We use cookies to keep you signed in. Cookie policy
We use cookies
CalculatorAI uses cookies to keep you signed in and remember your preferences. Optional cookies help us understand how the site is used. Cookie policy
About $0.003720 per task on GPT-5.6 Luna: 3 model calls, each resending the conversation so far. At 5,000 tasks a month that is $18.60.
An extraction agent reads an invoice, contract or form and returns structured fields — three calls, with the document itself as the long prompt and short tool results. On GPT-5.6 Luna, one task costs about $0.003720, and 5,000 tasks a month come to $18.60. The number that decides it is not the price per million tokens but how many calls one task takes — here 3 — because every call resends the whole conversation so far.
So the calls are not the same size. The first sends about 3,000 input tokens; the last, carrying everything before it, sends about 4,600 — 1.5× more. With so few steps the loop barely grows, so this is the one job where the input size of the document, not the number of steps, drives the price — and a small model usually does it well. The calculator below opens with this shape loaded: change the steps, the tool output and the volume to your own agent, and treat every figure here as an estimate from those assumptions, not a quote.
What One Agent Task Really Costs
Cost per task
One task · 5 calls to GPT-5.6 Terra
Cost per model call
$0.008640
averaged across 5 calls
Context growth
3.3×
1,800 tokens on the first call, 6,000 on the last
What drives one task
$0.0432At this volume
100 tasks · DayIf you ran this many tasks
100
$4.32
1,000
$43.20
10,000
$432.00
100,000
$4,320.00
What this figure assumes
Drop in a paystub, bank statement or screenshot — the AI reads it and fills these fields for you.
Income & Expense Tracker is where this stops being a one-off number: keep your real balances there and the projection updates itself.
Describe an invoice and the AI writes it. PDF without watermarks, free.
Same task shape on every row (1,000 system tokens cached, 2,000-token task, 500 tokens written and 300 returned by a tool per step). The last column doubles the steps: the input bill roughly quadruples because each call carries all the earlier ones.
| Model | Per task | Per month (5,000 tasks) | Per task at 6 steps |
|---|---|---|---|
| GPT-5.6 Luna | $0.003720 | $18.60 | $0.008700 |
| Claude Opus 5 | $0.0855 | $427.50 | $0.2025 |
| GPT-5.6 Terra | $0.0372 | $186.00 | $0.0870 |
Use cases